FPGA-based real-time MFCC extraction for automatic audio indexing on FM broadcast data

Abstract

This paper presents an FPGA-based real-time acoustic features extraction method based on MFCC (Mel-Frequency Cepstral Coefficients). The proposed system enables automatic audio indexing of broadcast data from the European standard Frequency Modulation (FM) radio band. Using modelbased design approach that reduces overall design time, we successfully implemented it on Virtex 6 FPGA clocked at more than 150 MHz. The experiments have shown on one hand, a high accuracy between the FPGA-based MFCC calculation and its Matlab-based reference model, and on the other hand, nearly similar result when used in music genre classification with sequential patterns mining techniques. Furthermore, the proposed system satisfies real-time requirements and is suitable for applications in embedded systems. Results are also discussed regarding operating frequencies and resources utilization.